switch to turn-based conversation

app.py

@@ -1,25 +1,25 @@
 # # Import required libraries
 
+import vocode
+from dotenv import load_dotenv
+from vocode import getenv
+from vocode.streaming.models.message import BaseMessage
+from vocode.streaming.models.synthesizer import *
+from vocode.streaming.models.agent import *
+from vocode.streaming.models.transcriber import *
+from vocode.streaming.synthesizer import *
 import gradio as gr
-import requests
-import json
 import os
-from pydub import AudioSegment
-import asyncio
 import logging
-import signal
-from vocode.streaming.streaming_conversation import StreamingConversation
-from vocode.helpers import create_streaming_microphone_input_and_speaker_output
-from vocode.streaming.transcriber import *
-from vocode.streaming.agent import *
-from vocode.streaming.synthesizer import *
-from vocode.streaming.models.transcriber import *
-from vocode.streaming.models.agent import *
-from vocode.streaming.models.synthesizer import *
-from vocode.streaming.models.message import BaseMessage
-import vocode
 
 
+from vocode.helpers import create_turn_based_microphone_input_and_speaker_output
+
+from vocode.turn_based.agent.chat_gpt_agent import ChatGPTAgent
+from vocode.turn_based.synthesizer import CoquiSynthesizer
+from vocode.turn_based.transcriber.whisper_transcriber import WhisperTranscriber
+from vocode.turn_based.turn_based_conversation import TurnBasedConversation
+
 system_prompt = """
 You are the evil lord Darth Vader. You answer all questions your subjects ask you, but do so with immense contempt and loathing.
 You may use any of the following lines or take inspiration from this conversational style where appropriate in your response.
@@ -76,51 +76,42 @@ logger = logging.getLogger(__name__)
 logger.setLevel(logging.DEBUG)
 
 
-async def main():
+def main():
     (
         microphone_input,
         speaker_output,
-    ) = create_streaming_microphone_input_and_speaker_output(
-        use_default_devices=True,
-        logger=logger,
-        use_blocking_speaker_output=True,
-    )
+    ) = create_turn_based_microphone_input_and_speaker_output(use_default_devices=True)
 
-    conversation = StreamingConversation(
+    conversation = TurnBasedConversation(
+        input_device=microphone_input,
         output_device=speaker_output,
-        transcriber=WhisperCPPTranscriber(
-            WhisperCPPTranscriberConfig.from_input_device(
-                microphone_input,
-                libname="/whisper.cpp/libwhisper.so",
-                fname_model="/whisper.cpp/models/ggml-tiny.bin",
-            )
-        ),
+        transcriber=WhisperTranscriber(api_key=getenv("OPENAI_API_KEY")),
         agent=ChatGPTAgent(
-            ChatGPTAgentConfig(
-                initial_message=BaseMessage(text="What up"),
-                prompt_preamble=system_prompt,
-            )
+            system_prompt=system_prompt,
+            initial_message="What up",
+            api_key=getenv("OPENAI_API_KEY"),
         ),
-        synthesizer=CoquiTTSSynthesizer(
-            CoquiTTSSynthesizerConfig.from_output_device(
+        synthesizer=CoquiSynthesizer(
+            CoquiSynthesizerConfig.from_output_device(
                 speaker_output,
                 tts_kwargs={
-                    "model_name": "tts_models/en/ljspeech/tacotron2-DDC_ph",
                     "voice_id": os.getenv("COQUI_VOICE_ID"),
                 }
-            )
+            ),
+            api_key=getenv("COQUI_API_KEY"),
         ),
         logger=logger,
     )
-    await conversation.start()
-    print("Conversation started, press Ctrl+C to end")
-    signal.signal(
-        signal.SIGINT, lambda _0, _1: asyncio.create_task(
-            conversation.terminate())
-    )
-    while conversation.is_active():
-        chunk = await microphone_input.get_audio()
-        conversation.receive_audio(chunk)
+    print("Starting conversation. Press Ctrl+C to exit.")
+    while True:
+        try:
+            input("Press enter to start recording...")
+            conversation.start_speech()
+            input("Press enter to end recording...")
+            conversation.end_speech_and_respond()
+        except KeyboardInterrupt:
+            break
+
 
-if __name__ == "__main__":
-    asyncio.run(main())
+demo = gr.Interface(fn=main, inputs="audio", outputs="audio")
+demo.launch()

requirements.txt

@@ -1 +1,2 @@
 vocode[io]
+dotenv